A New Image Auto-Segmentation Algorithm Based on PCNN

Abstract

Pulse Coupled Neural Networks (PCNN) is applied to image segmentation efficiently. Although the segmentation result with classical PCNN depends on the suitable concerned parameters, many experiments have shown that the segmentation result changed periodically with the calculation cyclic iteration times, N, after other parameters had been set. Therefore, how to decide the best iteration times N, is the key of applying PCNN to automated image segmentation. This paper brought forward a new edge-statistic algorithm based on calculation of connected regions, in order to automatically get the optimized value of N. An Edge-pixel Criterion was raised, and with it the algorithm calculated the valid edge pixels during the iteration process, and it meant that the maximum edge pixels were accordant with the best iteration times N, thereby the best segmentation result was achieved. The experiments show that the improved PCNN algorithm can promote the segmentation ability and has much better sensitivity than those methods based on image entropy or edge operator, and also has much stronger robustness of image noisy.